Skip to main content
Glama
office-powerpoint-mcp-server

office-powerpoint-mcp-server

Manage Shapes

manage_shapes

Add or delete styled visual cards, callout containers, arrows, and geometric shapes on PowerPoint slides to build clear visual layouts.

Instructions

Add styled visual cards, callout containers, arrows, or geometric shapes.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "slide_index": "<slide_index>",
      "action": "<action>"
    },
    "name": "manage_shapes"
  }
}

Input Schema

NameRequiredDescriptionDefault
topNoTop coordinate in inches
boldNoWhether inside text is bold
leftNoLeft coordinate in inches
textNoOptional text inside the shape
widthNoWidth in inches
actionYesShape action: 'add' or 'delete'
heightNoHeight in inches
auto_saveNoWhether to automatically save changes to file_path on disk
file_pathNoPath to presentation file within sandbox
font_sizeNoFont size in points
fill_colorNoHex fill color (e.g. '#F1F5F9' for cards)
shape_typeNoShape type: rectangle, rounded_rectangle, card, callout, arrow, ovalrectangle
text_colorNoHex text color e.g. '#1A1A1A'
shape_indexNoIndex of shape to delete (required for 'delete')
slide_indexYes0-based index of slide
border_colorNoHex border line color (e.g. '#CBD5E1')
border_width_ptNoBorder width in points
presentation_idNoIn-memory presentation ID

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false and destructiveHint=false, so the agent knows it mutates state, but the description adds nothing: it does not disclose that an 'add' writes to disk via auto_save=true, that 'delete' permanently removes a shape (a destructive operation the destructiveHint=false annotation undersells), or how presentation_id and file_path interact. For an 18-parameter mutation tool with a delete mode, this is a substantial disclosure gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence with no filler and no repetition of the title. It is efficient, though the brevity edges into under-specification rather than tightness, since a whole action mode is absent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, but the tool has 18 parameters, two action modes, disk-persistence via auto_save, and two ways to identify a presentation. Given that complexity, a single creation-only sentence leaves an agent unable to call the delete path or understand persistence side effects from the description alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter including the shape_type enum, colors, coordinates, and shape_index is already documented inline; the baseline of 3 applies. The description contributes only a loose signal that fill_color/border_color styling is expected ('styled visual cards'), and says nothing to clarify the required pairing of shape_index with action='delete'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a concrete verb and resource ('Add ... shapes') and enumerates shape kinds (cards, callouts, arrows, geometric), which is more specific than the title. But it only covers the 'add' half of the tool: the schema's 'action' enum includes 'delete', which the description never mentions, so an agent could reasonably conclude this tool only creates shapes. No sibling differentiation is offered against manage_text, add_image, or add_data_table.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no statement of when to prefer a shape over a table or image sibling, and no prerequisites such as needing an existing slide or presentation. The add-vs-delete decision, which is the central usage choice, is left entirely to the schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.